Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating exceptions or exclusions within a sentence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ento
    -0.81
    sonian
    -0.77
    eatured
    -0.76
    urred
    -0.76
    enth
    -0.76
    ierce
    -0.73
    accompan
    -0.73
    front
    -0.72
    orthy
    -0.72
    answered
    -0.71
    POSITIVE LOGITS
     occasional
    1.43
     maybe
    1.15
     perhaps
    1.04
     possibly
    0.91
     occasionally
    0.89
     minor
    0.84
     those
    0.82
     sporadic
    0.81
     one
    0.81
     briefly
    0.81
    Act Density 0.106%

    No Known Activations